中文
相关论文

相关论文: IG-Diff: Complex Night Scene Restoration with Illu…

200 篇论文

Image compression technology eliminates redundant information to enable efficient transmission and storage of images, serving both machine vision and human visual perception. For years, image coding focused on human perception has been…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Takahiro Shindo , Yui Tatsumi , Taiju Watanabe , Hiroshi Watanabe

Generating realistic 3D scenes is an area of growing interest in computer vision and robotics. However, creating high-quality, diverse synthetic 3D content often requires expert intervention, making it costly and complex. Recently, efforts…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Siyi Hu , Diego Martin Arroyo , Stephanie Debats , Fabian Manhardt , Luca Carlone , Federico Tombari

We present a novel approach designed to address the complexities posed by challenging, out-of-distribution data in the single-image depth estimation task. Starting with images that facilitate depth prediction due to the absence of…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Fabio Tosi , Pierluigi Zama Ramirez , Matteo Poggi

Recent advancements in diffusion models have been effective in learning data priors for solving inverse problems. They leverage diffusion sampling steps for inducing a data prior while using a measurement guidance gradient at each step to…

机器学习 · 计算机科学 2025-04-02 Rayhan Zirvi , Bahareh Tolooshams , Anima Anandkumar

Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we…

计算机视觉与模式识别 · 计算机科学 2021-12-15 Kui Jiang , Zhongyuan Wang , Zheng Wang , Chen Chen , Peng Yi , Tao Lu , Chia-Wen Lin

Decomposing a scene into its shape, reflectance, and illumination is a challenging but important problem in computer vision and graphics. This problem is inherently more challenging when the illumination is not a single light source under…

计算机视觉与模式识别 · 计算机科学 2021-08-27 Mark Boss , Raphael Braun , Varun Jampani , Jonathan T. Barron , Ce Liu , Hendrik P. A. Lensch

We introduce light diffusion, a novel method to improve lighting in portraits, softening harsh shadows and specular highlights while preserving overall scene illumination. Inspired by professional photographers' diffusers and scrims, our…

计算机视觉与模式识别 · 计算机科学 2023-05-09 David Futschik , Kelvin Ritland , James Vecore , Sean Fanello , Sergio Orts-Escolano , Brian Curless , Daniel Sýkora , Rohit Pandey

Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Junfeng Ni , Yu Liu , Ruijie Lu , Zirui Zhou , Song-Chun Zhu , Yixin Chen , Siyuan Huang

Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can…

图像与视频处理 · 电气工程与系统科学 2024-03-19 Haoyue Tang , Tian Xie , Aosong Feng , Hanyu Wang , Chenyang Zhang , Yang Bai

Recent progress in diffusion models has profoundly enhanced the fidelity of image generation, but it has raised concerns about copyright infringements. While prior methods have introduced adversarial perturbations to prevent style…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Namhyuk Ahn , Wonhyuk Ahn , KiYoon Yoo , Daesik Kim , Seung-Hun Nam

Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured data through a denoising process. When equipped with a guidance mechanism, these models can also…

机器学习 · 计算机科学 2026-05-04 Saeed Mohseni-Sehdeh , Walid Saad , Kei Sakaguchi , Tao Yu

Depth information provides valuable insights into the 3D structure especially the outline of objects, which can be utilized to improve the semantic segmentation tasks. However, a naive fusion of depth information can disrupt feature and…

计算机视觉与模式识别 · 计算机科学 2024-08-20 Wei Sun , Yuan Li , Qixiang Ye , Jianbin Jiao , Yanzhao Zhou

Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, non-uniform lighting, and strong light interference. Under limited supervision, this…

计算机视觉与模式识别 · 计算机科学 2026-04-28 Xining Ge , Weijun Yuan , Gengjia Chang , Xuyang Li , Shuhong Liu

Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions, and motion blur,…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Handing Xu , Zhenguo Nie , Tairan Peng , Huimin Pan , Xin-Jun Liu

The recovery of high-quality images from images corrupted by lens flare presents a significant challenge in low-level vision. Contemporary deep learning methods frequently entail training a lens flare removing model from scratch. However,…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Tianwen Zhou , Qihao Duan , Zitong Yu

Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on facial regions, neglecting degradation…

Despite the significant progress made by all-in-one models in universal image restoration, existing methods suffer from a generalization bottleneck in real-world scenarios, as they are mostly trained on small-scale synthetic datasets with…

计算机视觉与模式识别 · 计算机科学 2024-12-03 Hao Li , Xiang Chen , Jiangxin Dong , Jinhui Tang , Jinshan Pan

This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to…

计算机视觉与模式识别 · 计算机科学 2025-04-09 Jingzhi Bao , Guanying Chen , Shuguang Cui

Scene extrapolation -- the idea of generating novel views by flying into a given image -- is a promising, yet challenging task. For each predicted frame, a joint inpainting and 3D refinement problem has to be solved, which is ill posed and…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Shengqu Cai , Eric Ryan Chan , Songyou Peng , Mohamad Shahbazi , Anton Obukhov , Luc Van Gool , Gordon Wetzstein

Given an image of a natural scene, we are able to quickly decompose it into a set of components such as objects, lighting, shadows, and foreground. We can then envision a scene where we combine certain components with those from other…

计算机视觉与模式识别 · 计算机科学 2024-06-28 Jocelin Su , Nan Liu , Yanbo Wang , Joshua B. Tenenbaum , Yilun Du